[PATCH] D155662: [X86] Promote VAES implied feature to AVX2

Freddy, Ye via Phabricator via llvm-commits llvm-commits at lists.llvm.org
Wed Jul 19 01:36:56 PDT 2023


FreddyYe added a comment.

In D155662#4513714 <https://reviews.llvm.org/D155662#4513714>, @skan wrote:

> In D155662#4512974 <https://reviews.llvm.org/D155662#4512974>, @FreddyYe wrote:
>
>> As we noticed in SHA512's spec, it mentions AVX in "CPUID Feature Flag" only, but from software view, we can promote it to AVX2 as all machines having SHA512 have AVX2. Just like VAES here.
>
> Is it a good justification? Any pros from software view?

Like we did before for AVXNECONVERT, AVXIFMA, AVXVNNI. These ISA supports %ymm and operates on integers. And AVX2 is the first ISA is capable of that.


Repository:
  rG LLVM Github Monorepo

CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D155662/new/

https://reviews.llvm.org/D155662



More information about the llvm-commits mailing list